AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Efficient Learning of Event-based Dense Representation using Hierarchical Memories with Adaptive Update

Uday Kamal, Saibal Mukhopadhyay

ECCV 2024 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adaptive memory update instead of uniform update (ablation)hierarchical memory network · DSEC-Semanticlatency (ms): 5.8 -> 4.5Improved
use adaptive memory update instead of uniform update (ablation)hierarchical memory network · DSEC-SemanticmIoU: 49.7 -> 49.9Improved
raise update threshold from 0.5 to 0.7 (ablation)adaptive update · DSEC-SemanticmIoU: 49.9 -> 46.8Hurt
lower update threshold from 0.5 to 0.3 (ablation)adaptive update · DSEC-Semanticlatency (ms): 4.5 -> 4.8Hurt
use proposed adaptive hierarchical memory instead of HMNet-L3event-based segmentation · DSEC-SemanticmIoU: 57.1 -> 49.9 mIoU; 13.9 -> 4.5 msMixed
use proposed method instead of HMNet-L3 for depthevent-based depth estimation · MVSEC outdoor day1REL: 0.254 -> 0.292; latency 6.9 -> 2.3 msMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy